Home icon
Use Amazon Bedrock Intelligent Prompt Routing for cost and latency benefits

Machine Learning Blog



AWS has announced the general availability of Amazon Bedrock Intelligent Prompt Routing, a feature that dynamically routes requests between different foundation models to optimize cost and performance.

  • Supports models from Anthropic, Meta, and Nova families
  • Can use default pre-configured routers or create custom configurations
  • Reduces routing overhead to approximately 85 ms
  • Achieved up to 56% cost savings in internal tests
  • Allows routing between two models within the same model family

Key benefits include cost optimization, improved latency, and maintaining response quality by intelligently routing prompts to the most appropriate model based on complexity and cost.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.